identity_block.py

from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D

from keras.initializers import glorot_uniform
from custom_layers.scale_layer import Scale

def identity_block(X, f, filters, stage, block):
    """
    Implementation of the identity block as defined in Figure 3
    
    Arguments:
    X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
    f -- integer, specifying the shape of the middle CONV's window for the main path
    filters -- python list of integers, defining the number of filters in the CONV layers of the main path
    stage -- integer, used to name the layers, depending on their position in the network
    block -- string/character, used to name the layers, depending on their position in the network
    
    Returns:
    X -- output of the identity block, tensor of shape (n_H, n_W, n_C)
    """
    
    # defining name basis
    eps = 1.1e-5
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    scale_name_base = 'scale' + str(stage) + block + '_branch'
    
    # Retrieve Filters
    F1, F2, F3 = filters
    
    # Save the input value. You'll need this later to add back to the main path. 
    X_shortcut = X
    
    # First component of main path
    X = Conv2D(filters = F1, kernel_size = (1, 1), strides = (1,1), padding = 'valid', use_bias=False, name = conv_name_base + '2a', kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(epsilon = eps, axis = 3, name = bn_name_base + '2a')(X)
    X = Scale(axis = 3, name = scale_name_base + '2a')(X)
    X = Activation('relu')(X)
    
    # Second component of main path
    X = Conv2D(filters = F2, kernel_size = (f, f), strides = (1,1), padding = 'same', use_bias=False, name = conv_name_base + '2b', kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(epsilon = eps, axis = 3, name = bn_name_base + '2b')(X)
    X = Scale(axis = 3, name = scale_name_base + '2b')(X)
    X = Activation('relu')(X)

    # Third component of main path
    X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = 'valid', use_bias=False, name = conv_name_base + '2c', kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(epsilon = eps, axis = 3, name = bn_name_base + '2c')(X)
    X = Scale(axis = 3, name = scale_name_base + '2c')(X)

    # Final step: Add shortcut value to main path, and pass it through a RELU activation
    X = Add()([X,X_shortcut])
    X = Activation('relu')(X)
    
    return X